The following is a summary of “Measurement of the level of consciousness by AVPU scale assessment system based on automated video and speech recognition technology,” published in the December 2023 issue of Emergency Medicine by Choi, et al.

For a study, researchers sought to develop an alert/verbal/painful/unresponsive (AVPU) scale assessment system based on automated video and speech recognition technology (AVPU-AVSR), enabling automatic evaluation of a patient’s level of consciousness. The system’s performance was evaluated through clinical simulation.

The AVPU-AVSR system was developed utilizing a whole-body camera, face camera, and microphone. It automatically extracted essential audiovisual features from recorded video files to assess the AVPU score. Arm movement, pain stimulus, and eyes-open state were determined using a rule-based approach with landmarks from pre-trained pose and face estimation models. Verbal stimuli were extracted using a pre-trained speech-recognition model. Simulations involved 12 simulated patients across 16 scenarios (4 for each AVPU category). The system’s accuracy, sensitivity, and specificity were assessed.

A total of 192 cases with 12 simulated patients were assessed using the AVPU-AVSR system, achieving a multi-class accuracy of 0.95 (95% CI 0.92–0.98). The sensitivity and specificity (95% CIs) for detecting impaired consciousness were 1.00 (0.97–1.00) and 0.88 (0.75–0.95), respectively. Each extracted feature demonstrated sensitivity and specificity ranging from 0.88 to 1.00 and 0.98 to 1.00, respectively.

The AVPU-AVSR system demonstrated high accuracy in assessing consciousness levels during clinical simulation. It holds promise for implementation in clinical practice, offering automated mental status assessment.

Reference: sciencedirect.com/science/article/abs/pii/S073567572300517X